gsp-hud-readability-audit
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill evaluates external data sources, including game HUD screenshots and layout code, to perform its core audit function. While it lacks explicit delimiters for untrusted data, the skill's capabilities are limited to generating descriptive analysis and writing to specific local project files, presenting no significant security risk.
- Ingestion points: Audited layout code and screenshots (SKILL.md)
- Boundary markers: No explicit markers or instructions for audited content
- Capability inventory: File writing restricted to specific paths in docs/game-studio/audit/ (SKILL.md)
- Sanitization: None observed for external content
Audit Metadata